prompt-injection

Lessons from the field. Always landing on my feet.

All Cloud Security Identity Security Microsoft Sentinel AI Security Detection Engineering Microsoft Defender Threat Detection Entra ID Container Security Zero Trust DevSecOps Infrastructure as Code Agentic AI 3 posts
Jerrad Dahlager
Jerrad Dahlager, CISSP, CCSP Cloud Security Architect · Adjunct Instructor
About me →
AI Security

Agent 365 Launch Playbook: I Tested the Defender Response for AI Agent Attacks

When I published this lab on April 20, Microsoft had announced that Agent 365 would become generally available on May 1, 2026. It reached that milestone; the launch-week security question behind the lab still matters. I wanted to answer a different …

16 min read Read more →
AI Security

Block Prompt Injection at the Network Layer with Microsoft Entra Prompt Injection Protection

A while back I built an LLM Firewall with AWS Lambda, an API screening demo that returns an allow/block decision for common prompt-injection patterns. That lab does not connect to an LLM; deploying the pattern in front of a model requires a separate …

15 min read Read more →
AI Security

Building an LLM Prompt Injection Firewall with AWS Lambda

AWS continues to enhance its generative AI security capabilities, with improved prompt attack filtering now available in Amazon Bedrock Guardrails. Despite these advances, a significant gap remains: organizations are deploying LLM capabilities faster …

14 min read Read more →